© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13757
    Prev
    Next
    INDEX
    Explanations

    assert

    np_acts-logits-general · gemini-2.5-flash-lite

    what ... when

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ת
    0.37
     ตาม
    0.36
     המ
    0.36
     ב
    0.36
     הל
    0.34
    惀
    0.34
     대로
    0.33
    Ｘ
    0.33
     עם
    0.33
     על
    0.33
    POSITIVE LOGITS
     quando
    0.40
     pathophysiology
    0.39
     fárm
    0.38
     intraper
    0.38
     intramolecular
    0.37
     ketika
    0.36
     when
    0.35
     ergonom
    0.35
     physiologically
    0.35
     Neend
    0.35
    Activations Density 0.000%

    No Known Activations